Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45651
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and exclamations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    384
    +0.12
    0.6%
    171
    +0.12
    0.5%
    674
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.34
    107
    +0.12
    0.08
    373
    +0.11
    -0.22
    Negative Logits
     colleg
    -0.60
     athletics
    -0.59
     Vampire
    -0.59
     abound
    -0.59
     murd
    -0.58
     sl
    -0.57
     wholes
    -0.56
     Shank
    -0.56
     spur
    -0.55
     Silk
    -0.55
    POSITIVE LOGITS
    estamp
    0.95
    cknowled
    0.93
     largeDownload
    0.85
    \":
    0.81
    roxy
    0.81
    sectional
    0.76
    ths
    0.76
    aturation
    0.72
    onnaissance
    0.71
    ãĥ´ãĤ¡
    0.70
    Activations Density 12.303%

    No Known Activations